INDEX

Explanations

words related to a specific place or name, specifically "Marg"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Margaret" or its variants

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fulness

-0.85

pmwiki

-0.79

enegger

-0.78

ctor

-0.76

 hearing

-0.70

ÄŁ

-0.70

spe

-0.70

FUL

-0.70

INESS

-0.69

ãģ¦

-0.68

POSITIVE LOGITS

aret

1.18

olis

1.06

inal

0.97

reet

0.94

inally

0.88

acies

0.87

olicy

0.86

iana

0.86

arine

0.83

inals

0.83

Activations Density 0.013%

words related to a specific place or name, specifically "Marg"

occurrences of the name "Margaret" or its variants

No Comments

No Known Activations